# 503 server Error

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F503-server-error%2F166479%3E%5C
**Category:** Models\
**Created:** [August 12, 2025, 5:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F503-server-error%2F166479 "2025-08-12T05:19:00Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![chawla7](https://avatars.discourse-cdn.com/v4/letter/c/9fc348/32.png) [@chawla7](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchawla7)%5C
**Post date:** [August 12, 2025, 5:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F503-server-error%2F166479%2F1 "2025-08-12T05:19:00Z")

</div>

I”m getting following error. can someone please help me?

huggingface\_hub.errors.HfHubHTTPError: 503 Server Error: Service Temporarily Unavailable for url: [/static-proxy?url=https%3A%2F%2Frouter.huggingface.co%2Ffeatherless-ai%2Fv1%2Fchat%2Fcompletions%5D(https%3A%2F%2Frouter.huggingface.co%2Ffeatherless-ai%2Fv1%2Fchat%2Fcompletions)

Below is the code I’m using

## langchain integration package

from langchain\_huggingface import ChatHuggingFace, HuggingFaceEndpoint

from dotenv import load\_dotenv

from huggingface\_hub import login

acces\_token\_read = XXXXXXXXXXXXXXXXXXXXXXXXXXXXX

login(token = acces\_token\_read)

load\_dotenv()

llm1 = HuggingFaceEndpoint(

```
repo_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0", 

task = "text-generation", 

provider = "auto"

```

)

model = ChatHuggingFace(llm=llm1)

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [August 12, 2025, 7:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F503-server-error%2F166479%2F2 "2025-08-12T07:20:36Z")

</div>

Oh… Same here…

```py
# pip install -U huggingface_hub
import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="auto",
    api_key=os.getenv("HF_TOKEN", None)
)

completion = client.chat.completions.create(
    #model="HuggingFaceTB/SmolLM3-3B",
    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
    messages=[
        {
            "role": "user",
            "content": "What is the capital of France?"
        }
    ],
)
# huggingface_hub.errors.HfHubHTTPError: 503 Server Error: Service Temporarily Unavailable for url: /static-proxy?url=https%3A%2F%2Frouter.huggingface.co%2Ffeatherless-ai%2Fv1%2Fchat%2Fcompletions

print(completion.choices[0].message)

```
